helix.mcp

Investigate .NET CI failures using the hlx CLI tool via bash. USE FOR: checking Helix job status, searching build logs, downloading test results, AzDO build timeline analysis — when MCP tools aren't loaded, when the MCP server isn't configured or fails to start, or when scripting with JSON output and jq. DO NOT USE FOR: tasks where Helix/AzDO MCP tools are already available in context (prefer ci-analysis skill when MCP server is loaded). INVOKES: bash (hlx CLI commands with --json output).

{what this skill teaches agents}

Audit pattern for comparing WorkItemSummary (list API) fields against WorkItemDetails (per-item API) after a Helix.Client SDK bump

Domain-layer normalizer + JSON-stable cache key pattern for filter types with server-side defaults and case-insensitive fields.

Strict unknown-parameter rejection for MCP tools: Stage A (UnmappedMemberHandling.Disallow) + Stage B (did-you-mean CallToolFilter).

Audit MCP/CLI tool parameter surface against underlying REST API capabilities to find silently-dropped params.

Test MCP CallToolFilter behavior with real CallToolRequestParams and McpServerTool invocation.

Completion-safe bucketing for Helix work items with nullable exit codes

Rename MCP tool parameters when the wire schema drifted from semantic intent.

Design filter/enum parameters for MCP tools consumed by LLM clients, balancing expressiveness with discoverability.

Add MCP enum presets while accepting schema-invisible aliases in validation logic.

How to audit NuGet dependencies in this repo for updates, deprecations, and vulnerabilities

How to safely remove implicit constructor fallbacks for injected dependencies

Pattern for searching across many items with ranked priority and early termination

Refresh a project knowledgebase after code/doc updates by separating resolved findings from remaining follow-up work and durable facts.

Pattern for migrating MCP tools from string returns to UseStructuredContent typed returns

STRIDE threat modeling patterns specific to MCP servers

Write MCP tool descriptions and failure messages that route callers to the right adjacent tools when workflows vary by repo, environment, or artifact availability.

How to perform root-path containment checks without weakening security on case-sensitive filesystems

{what this skill teaches agents}

{what this skill teaches agents}